We Keep Coding

How to extract radiobutton / checkbox information with python from a pdf-file?

i would like to get the radio-button / checkbox information from a pdf-document -
I had a look at pdfplumber and pypdf2 - but was not able to find a solution with this modules.
I can parse the text using this code - but for the radio-buttons i get only the text - but no information which button (or checkbox) is selected.
import pdfplumber
import os
import sys
if __name__ == '__main__':
path = os.path.abspath(os.path.dirname(sys.argv[0]))
fn = os.path.join(path, "input.pdf")
pdf = pdfplumber.open(fn)
page = pdf.pages[0]
text = page.extract_text()
I have also uploaded an example file here:
https://easyupload.io/8y8k2v
Is there any way to get this information from the pdf-file using python?

I think i found a solution using pdfplumber -
(probably not elegant - but i can check if the radio-buttons are selected or not)
Generally:
i read all chars and all curves for all pages
then i sort all elements by x and y (to get the chars and elements in the correct order like in the pdf)
then i concatenate the cars and add also blanks when the distance between the chars is longer than in a word
i check the pts-information for the carves and get so the information if the radio button is selected or not
the final lines and yes/not informatin i store in a list line-by-line for furhter working
import pdfplumber
import os
import sys
fn = os.path.join(path, "input.pdf")
pdf = pdfplumber.open(fn)
finalContent = []
for idx,page in enumerate(pdf.pages, start=1):
print(f"Reading page {idx}")
contList = []
for e in page.chars:
tmpRow = ["char", e["text"], e["x0"], e["y0"]]
contList.append(tmpRow)
for e in page.curves:
tmpRow = ["curve", e["pts"], e["x0"], e["y0"]]
contList.append(tmpRow)
contList.sort(key=lambda x: x[2])
contList.sort(key=lambda x: x[3], reverse=True)
workContent = []
workText = ""
workDistCharX = False
for e in contList:
if e[0] == "char":
if workDistCharX != False and \
(e[2] - workDistCharX > 20 or e[3] - workDistCharY < -2):
workText += " / "
workText += e[1]
workDistCharX = e[2]
workDistCharY = e[3]
continue
if e[0] == "curve":
if workText != "":
workContent.append(workText)
workText = ""
if e[1][0][0] < 100:
tmpVal = "SELECT-YES"
else:
tmpVal = "SELECT-NO"
workContent.append(f"CURVE {tmpVal}, None, None")
finalContent.extend(workContent)
workContent = "\n".join(workContent)

How to scrape data from PDF into Excel

I am trying to scrape the data from PDF and get it saved into an excel file. This is the pdf I needed: https://www.medicaljournals.se/acta/content_files/files/pdf/98/219/Suppl219.pdf
However, I need to scrape not all the data but the following one (below), and then saved it to excel in different cells:
From page 5, starting from P001 to and including Introduction - there is a P number, title, people names, and Introduction.
For now, I can only convert a PDF file into text (my code below) and save it all in one cell, but I need it to be separated into a different cells
import PyPDF2 as p2
PDFfile = open('Abstract Book from the 5th World Psoriasis and Psoriatic Arthritis
Conference 2018.pdf', 'rb')
pdfread = p2.PdfFileReader(PDFfile)
pdflist = []
i = 6
while i<pdfread.getNumPages():
pageinfo = pdfread.getPage(i)
#print(pageinfo.extractText())
i = i + 1
pdflist.append(pageinfo.extractText().replace('\n', ''))
print(pdflist)

The main you need is 'header' regex as 15 UPPERcase letters and 'article' regex letter 'P' and 3 digits.
One more regex helps you to divide your text by any of keywords
article_re = re.compile(r'[P]\d{3}') #P001: letter 'P' and 3 digits
header_re = re.compile(r'[A-Z\s\-]{15,}|$') #min 15 UPPERCASE letters, including '\n' '-' and
key_word_delimeters = ['Peoples', 'Introduction','Objectives','Methods','Results','Conclusions','References']
file = open('data.pdf', 'rb')
pdf = pdf.PdfFileReader(file)
text = ''
for i in range(6, 63):
text += pdf.getPage(i).extractText() # all text in one variable
articles = []
for article in re.split(article_re, text):
header = re.match(header_re, article) # recieving a match
other_text = re.split(header_re, article)[1] # recieving other text
if header:
header = header.group() # get text from match
item = {'header': header}
first_name_letter = header[-1] # save the first letter of name to put it in right position. Some kind of HOT BUGFIX
header = header[:-1] # cut last character: the first letter of name
header = header.replace('\n', '') #delete linebreakers
header = header.replace('-', '') #delete line break symbol
other_text = first_name_letter + other_text
data_array = re.split(
'Introduction:|Objectives:|Methods:|Results:|Conclusions:|References:',
other_text)
for key, data in zip(key_word_delimeters, data_array):
item[key] = data.replace('\n', '')
articles.append(item)

function inside for loop in python

how to call function inside for loop with PYTHON
must call this funtion
def EE():
print("dd")
inside this
def upload_file(request):
if request.method == 'POST':
form = UploadFileForm(request.POST, request.FILES)
files = request.FILES.getlist('file_field')
fs = FileSystemStorage()
for f in files:
filename = fs.save(f.name, f)
ee=EE()
print(ee)
number_of_files=len(files)
uploaded_file_url = fs.url(filename)
return render(request, 'core/simple_upload.html', {
# 'uploaded_file_url': uploaded_file_url
})

The way you have written is correct. Since your function doesn't returns any value, I doubt whether you will receive the desired output.
Assuming the function to be called and the other are in the same scope.
def sample_function():
return "This is a sample function."
def main_function():
# function call
x = sample_function()
print(x)
# add your logic here.
Hope this will help.

def sentence_finder(text, word):
sentences = sent_tokenize(text)
return [sent for sent in sentences if word in word_tokenize(sent)]
def EE(filename,no_of_files):
for i in range(no_of_files):
try:
print('\n')
print(i+1)
pdfFileObj = open(filename, 'rb')
pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
num_pages = pdfReader.numPages
count = 0
text = ""
# The while loop will read each page
while count < num_pages:
pageObj = pdfReader.getPage(count)
count += 1
text += pageObj.extractText()
# This if statement exists to check if the above library returned #words. It's done because PyPDF2 cannot read scanned files.
if text != "":
text = text
# If the above returns as False, we run the OCR library textract to #convert scanned/image based PDF files into text
else:
text = textract.process(filename, method='tesseract', language='eng')
# select relevnt section
# education qulification
textt = re.search(r'EDUCATION\n.*?SKILLS', text, re.DOTALL).group()
edu_qulification = textt[textt.find('\n') + 1:textt.rfind('\n')]
srt1=edu_qulification.lower()
# print(edu_qulification)
str12 = srt1.replace("\n", ". ")
str2 = str12.replace("m.s.", "master")
# print(str2)
syn = synonyms = wordnet.synsets('degree')
syn_set1 = list(chain.from_iterable([word.lemma_names() for word in synonyms]))
syn = synonyms = wordnet.synsets('BACHELOR')
syn_set2 = list(chain.from_iterable([word.lemma_names() for word in synonyms]))
syn = synonyms = wordnet.synsets('Master')
syn_set3 = list(chain.from_iterable([word.lemma_names() for word in synonyms]))
listone = ['bsc','be', 'btech']
listtwo =['m.s.']
mergedlist = listone + syn_set1 + syn_set2 + syn_set3 + listtwo
# print(mergedlist)
for i in mergedlist:
sent_part=sentence_finder(str2,i)
# print(sent_part)
if not sent_part:
pass
else:
Digree = sentence_finder(str2, i)
synn = synonyms = wordnet.synsets('university')
syn_seta = list(chain.from_iterable([word.lemma_names() for word in synonyms]))
synn = synonyms = wordnet.synsets('institute')
syn_setb= list(chain.from_iterable([word.lemma_names() for word in synonyms]))
synn = synonyms = wordnet.synsets('college')
syn_setc = list(chain.from_iterable([word.lemma_names() for word in synonyms]))
listthree=['center']
mergedlistt = listthree + syn_seta + syn_setb + syn_setc
# print(mergedlistt)
for j in mergedlistt:
sent_partt = sentence_finder(str2, j)
# print(sent_partt)
if not sent_partt:
pass
else:
University = sentence_finder(str2, j)
# Digree = sentence_finder(str2, 'BACHELOR')
# University = sentence_finder(str2, 'UNIVERSITY')
print(Digree)
print(University)
print(".................................................................")
# print(University)
except:
print("No Education Qualification mentioned")

split() issues with pdf extractText()

I'm working on a minor content analysis program that I was hoping that I could have running through several pdf-files and return the sum of frequencies that some specific words are mentioned in the text. The words that are searched for are specified in a separate text file (list.txt) and can be altered. The program runs just fine through files with .txt format, but the result is completely different when running the program on a .pdf file. To illustrate, the test text that I have the program running trhough is the following:
"Hello
This is a product development notice
We’re working with innovative measures
A nice Innovation
The world that we live in is innovative
We are currently working on a new process
And in the fall, you will experience our new product development introduction"
The list of words grouped in categories are the following (marked in .txt file with ">>"):
innovation: innovat
product: Product, development, introduction
organization: Process
The output from running the code with a .txt file is the following:
Whereas the ouput from running it with a .pdf is the following:
As you can see, my issue is pertaining to the splitting of the words, where in the .pdf output i can have a string like "world" be split into 'w','o','rld'. I have tried to search for why this happens tirelessly, without success. As I am rather new to Python programming, I would appreciate any answe or direction to where I can fin and answer to why this happens, should you know any source.
Thanks
The code for the .txt is as follows:
import string, re, os
import PyPDF2
dictfile = open('list.txt')
lines = dictfile.readlines()
dictfile.close()
dic = {}
scores = {}
i = 2011
while i < 2012:
f = 'annual_report_' + str(i) +'.txt'
textfile = open(f)
text = textfile.read().split() # lowercase the text
print (text)
textfile.close()
i = i + 1
# a default category for simple word lists
current_category = "Default"
scores[current_category] = 0
# import the dictionary
for line in lines:
if line[0:2] == '>>':
current_category = line[2:].strip()
scores[current_category] = 0
else:
line = line.strip()
if len(line) > 0:
pattern = re.compile(line, re.IGNORECASE)
dic[pattern] = current_category
# examine the text
for token in text:
for pattern in dic.keys():
if pattern.match( token ):
categ = dic[pattern]
scores[categ] = scores[categ] + 1
print (os.path.basename(f))
for key in scores.keys():
print (key, ":", scores[key])
While the code for the .pdf is as follows:
import string, re, os
import PyPDF2
dictfile = open('list.txt')
lines = dictfile.readlines()
dictfile.close()
dic = {}
scores = {}
i = 2011
while i < 2012:
f = 'annual_report_' + str(i) +'.pdf'
textfile = open(f, 'rb')
text = PyPDF2.PdfFileReader(textfile)# lowercase the text
for pageNum in range(0, text.numPages):
texts = text.getPage(pageNum)
textfile = texts.extractText().split()
print (textfile)
i = i + 1
# a default category for simple word lists
current_category = "Default"
scores[current_category] = 0
# import the dictionary
for line in lines:
if line[0:2] == '>>':
current_category = line[2:].strip()
scores[current_category] = 0
else:
line = line.strip()
if len(line) > 0:
pattern = re.compile(line, re.IGNORECASE)
dic[pattern] = current_category
# examine the text
for token in textfile:
for pattern in dic.keys():
if pattern.match( token ):
categ = dic[pattern]
scores[categ] = scores[categ] + 1
print (os.path.basename(f))
for key in scores.keys():
print (key, ":", scores[key])

Searching a file for matches between two values and outputting search hits in Python

I am (attempting) to write a program that searches through a hex file for instances of a hex string between two values, eg. Between D4135B and D414AC, incrementing between the first value until the second is reached- D4135B, D4135C, D4135D etc etc.
I have managed to get it to increment etc, but it’s the search part I am having trouble with.
This is the code I have so far, it's been cobbled together from other places and I need to make it somehow output all search hits into the output file (file_out)
I have exceeded the limit of my Python understanding and I'm sure there's probably a much easier way of doing this. I would be very grateful for any help.
def search_process(hx): # searching for two binary strings
global FLAG
while threeByteHexPlusOne != threeByteHex2: #Keep incrementing until second value reached
If Flag:
if hx.find(threeByteHex2) != -1:
FLAG = False #If threeByteHex = ThreeByteHexPlusOne, end search
Print (“Reached the end of the search”,hx.find(threeByteHexPlusOne))
Else:
If hx.find(threeByteHexPlusOne) != -1:
FLAG = True
Return -1 #If no results found
if __name__ == '__main__':
try:
file_in = open(FILE_IN, "r") #opening input file
file_out = open(FILE_OUT, 'w') #opening output file
hx_read = file_in.read #read from input file
tmp = ''
found = ''
while hx_read: #reading from file till file is empty
hx_read = tmp + hx_read
pos = search_process(hx_read)
while pos != -1:
hex_read = hx_read[pos:]
if FLAG:
found = found + hx_read
pos = search_process(hx_read)
tmp = bytes_read[]
hx_read = file_in.read
file_out.write(found) #writing to output file
except IOError:
print('FILE NOT FOUND!!! Check your filename or directory/PATH')

Here's a program that looks through a hex string from a file 3 bytes at a time and if the 3-byte hex string is between the given hex bounds, it writes it to another file. It makes use of generators to make getting the bytes from the hex string a little cleaner.
import base64
import sys
_usage_string = 'Usage: python {} <input_file> <output_file>'.format(sys.argv[0])
def _to_base_10_int(value):
return int(value, 16)
def get_bytes(hex_str):
# Two characters equals one byte
for i in range(0, len(hex_str), 2):
yield hex_str[i:i+2]
def get_three_byte_hexes(hex_str):
bytes = get_bytes(hex_str)
while True:
try:
three_byte_hex = next(bytes) + next(bytes) + next(bytes)
except StopIteration:
break
yield three_byte_hex
def find_hexes_in_range(hex_str, lower_bound_hex, upper_bound_hex):
lower_bound = _to_base_10_int(lower_bound_hex)
upper_bound = _to_base_10_int(upper_bound_hex)
found = []
for three_byte_hex in get_three_byte_hexes(hex_str):
hex_value = _to_base_10_int(three_byte_hex)
if lower_bound <= hex_value < upper_bound:
found.append(three_byte_hex)
return found
if __name__ == "__main__":
try:
assert(len(sys.argv) == 3)
except AssertionError:
print _usage_string
sys.exit(2)
file_contents = open(sys.argv[1], 'rb').read()
hex_str = base64.decodestring(file_contents).encode('hex')
found = find_hexes_in_range(hex_str, 'D4135B', 'D414AC')
print('Found:')
print(found)
if found:
with open(sys.argv[2], 'wb') as fout:
for _hex in found:
fout.write(_hex)
Check out some more info on generators here